AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

ARTEM: Enhancing Large Language Model Agents with Spatial-Temporal Episodic Memory

Cassandra Hui-Ming Tan, Budhitama Subagdja, Ah-Hwee Tan

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Long-context and personalized retrieval · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use LLM-based answer synthesis on top of STEM (ARTEM vs STEM)STEM · single-event queries (Bin 1)F1: 0.55 -> 0.68Improved
add LLM synthesis to STEM for latest-event queriesSTEM · Latest time instructionF1: 0.54 -> 0.66Improved
add LLM synthesis to STEM for full-event-detail cuesSTEM · Full event details cueF1: 0.5 -> 0.67Improved
replace STEM retrieval with LLM synthesis on null queriesSTEM · 0 matching eventsF1: 1.00 -> 0.95Hurt
replace STEM with ARTEM on chronological recallSTEM · chronological taskF1: 0.644 -> 0.585Hurt
replace STEM with ARTEM on simple recallSTEM · simple recallF1: 0.733 -> 0.709Hurt
use STEM episodic memory instead of in-context gemini-2-pro for chronological recallgemini-2-pro · chronological taskF1: 0.290 -> 0.644Improved
use reasoning-optimized model o1 in-context instead of gpt-4ogpt-4o · chronological taskF1: 0.204 -> 0.052Hurt
fine-tune gpt-4o-mini instead of in-context for null queriesgpt-4o-mini · 0 matching eventsF1: 0.51 -> 0.00Hurt
fine-tune gpt-4o-mini instead of in-context for single-event queriesgpt-4o-mini · 1 matching eventF1: 0.54 -> 0.83Improved
fine-tune gpt-4o-mini instead of in-context for 6+ eventsgpt-4o-mini · 6+ matching eventsF1: 0.50 -> 0.19Hurt
add RAG to gpt-4o-mini instead of in-contextgpt-4o-mini · 6+ matching eventsF1: 0.50 -> 0.62Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy